An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

EACL 2021  ·  Markus Eberts, Adrian Ulges ·

We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity level. To do so, a multi-task approach is followed that builds upon coreference resolution and gathers relevant signals via multi-instance learning with multi-level representations combining global entity and local mention information. We achieve state-of-the-art relation extraction results on the DocRED dataset and report the first entity-level end-to-end relation extraction results for future reference. Finally, our experimental results suggest that a joint approach is on par with task-specific learning, though more efficient due to shared parameters and training steps.

PDF Abstract EACL 2021 PDF EACL 2021 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Joint Entity and Relation Extraction DocRED JEREX Relation F1 40.38 # 4
Relation Extraction DocRED JEREX-BERT-base F1 60.40 # 30
Ign F1 58.44 # 30
Relation Extraction ReDocRED JEREX F1 72.57 # 6
Ign F1 71.45 # 6


No methods listed for this paper. Add relevant methods here